Using machine learning models to simulate performance of vacuum tube audio hardware

Abstract

In some embodiments, a hardware simulation computing system is provided. The hardware simulation computing system is configured to provide audio signals from a low-performance audio device as input to a machine learning model capable of exhibiting temporal dynamic behavior; to update the machine learning model based on a comparison of outputs of the machine learning model to ground truth audio signals from a high-performance audio device; and to repeat the providing and updating actions until a completion threshold is reached to create a trained machine learning model.

What is claimed is: 
     
         1 . A non-transitory computer-readable medium having logic stored thereon that, in response to execution by one or more processors of a hardware simulation computing system, causes the hardware simulation computing system to perform actions for training a machine learning model to simulate performance of a high-performance audio device, the actions comprising:
 providing, by the hardware simulation computing system, audio signals from a low-performance audio device as input to the machine learning model, wherein the machine learning model is capable of exhibiting temporal dynamic behavior;   updating, by the hardware simulation computing system, the machine learning model based on a comparison of outputs of the machine learning model to ground truth audio signals from a high-performance audio device;   repeating, by the hardware simulation computing system, the providing and updating actions until a completion threshold is reached to create a trained machine learning model; and   storing, by the hardware simulation computing system, the trained machine learning model in a model data store.   
     
     
         2 . The non-transitory computer-readable medium of  claim 1 , wherein the machine learning model capable of exhibiting temporal dynamic behavior is a recurrent neural network. 
     
     
         3 . The non-transitory computer-readable medium of  claim 2 , wherein the recurrent neural network is a WaveRNN model. 
     
     
         4 . The non-transitory computer-readable medium of  claim 1 , wherein the actions further comprise sparsifying the machine learning model while repeating the providing and updating actions. 
     
     
         5 . The non-transitory computer-readable medium of  claim 1 , wherein the actions further comprise transmitting the trained machine learning model to an edge device for execution. 
     
     
         6 . The non-transitory computer-readable medium of  claim 1 , wherein the actions further comprise:
 contemporaneously receiving an audio signal from the low-performance audio device and an audio signal from the high-performance audio device based on a common audio source; and   storing the audio signals as a training pair in a training data store.   
     
     
         7 . The non-transitory computer-readable medium of  claim 6 , wherein the audio signal from the low-performance audio device provided as input to the machine learning model and the ground truth audio signal from the high-performance audio device are from a training pair retrieved from the training data store. 
     
     
         8 . The non-transitory computer-readable medium of  claim 1 , wherein the high-performance audio device includes one or more vacuum tubes, and wherein the low-performance audio device does not include a vacuum tube. 
     
     
         9 . A non-transitory computer-readable medium having logic stored thereon that, in response to execution by one or more processors of a computing device, causes the computing device to perform actions comprising:
 receiving, by the computing device, an audio signal from a low-performance audio device;   providing, by the computing device, the audio signal as input to a trained machine learning model to generate an output that simulates an audio signal from a high-performance audio device, wherein the trained machine learning model is capable of exhibiting temporal dynamic behavior; and   providing, by the computing device, the simulated audio signal for presentation by a loudspeaker.   
     
     
         10 . The non-transitory computer-readable medium of  claim 9 , wherein the trained machine learning model capable of exhibiting temporal dynamic behavior is a recurrent neural network. 
     
     
         11 . The non-transitory computer-readable medium of  claim 10 , wherein the recurrent neural network is a WaveRNN model. 
     
     
         12 . The non-transitory computer-readable medium of  claim 9 , wherein the trained machine learning model is sparsified during training. 
     
     
         13 . The non-transitory computer-readable medium of  claim 9 , wherein the computing device is an edge device. 
     
     
         14 . The non-transitory computer-readable medium of  claim 9 , wherein the high-performance audio device includes one or more vacuum tubes, and wherein the low-performance audio device does not include one or more vacuum tubes. 
     
     
         15 . A system for training a machine learning model, the system comprising:
 at least one audio source;   a low-performance audio device configured to receive audio signals from the audio source and;   a high-performance audio device configured to receive audio signals from the audio source contemporaneously with the low-performance audio device; and   a hardware simulation computing system communicatively coupled to the low-performance audio device and the high-performance audio device, wherein the hardware simulation computing system includes logic that, in response to execution by one or more processors of the hardware simulation computing system, causes the hardware simulation computing system to perform actions for training a machine learning model to simulate performance of the high-performance audio device, the actions comprising:
 providing, by the hardware simulation computing system, audio signals from the low-performance audio device as input to the machine learning model, wherein the machine learning model is capable of exhibiting temporal dynamic behavior; 
 updating, by the hardware simulation computing system, the machine learning model based on a comparison of outputs of the machine learning model to ground truth audio signals from a high-performance audio device; 
 repeating, by the hardware simulation computing system, the providing and updating actions until a completion threshold is reached to create a trained machine learning model; and 
 storing, by the hardware simulation computing system, the trained machine learning model in a model data store. 
   
     
     
         16 . The system of  claim 15 , wherein the machine learning model capable of exhibiting temporal dynamic behavior is a recurrent neural network. 
     
     
         17 . The system of  claim 16 , wherein the recurrent neural network is a WaveRNN model. 
     
     
         18 . The system of  claim 16 , wherein the actions further comprise sparsifying the machine learning model while repeating the providing and updating actions. 
     
     
         19 . The system of  claim 15 , wherein the actions further comprise transmitting the trained machine learning model to an edge device for execution. 
     
     
         20 . The system of  claim 15 , wherein the high-performance audio device includes one or more vacuum tubes, and wherein the low-performance audio device does not include any vacuum tubes.